In this paper we present S3R-Net, the Self-Supervised Shadow Removal Network. The two-branch WGAN model achieves self-supervision relying on the unify-and-adaptphenomenon - it unifies the style of the output data and infers its characteristics from a database of unaligned shadow-free reference images. This approach stands in contrast to the large body of supervised frameworks. S3R-Net also differentiates itself from the few existing self-supervised models operating in a cycle-consistent manner, as it is a non-cyclic, unidirectional solution. The proposed framework achieves comparable numerical scores to recent selfsupervised shadow removal models while exhibiting superior qualitative performance and keeping the computational cost low.
Cite
@article{arxiv.2404.12103,
title = {S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal},
author = {Nikolina Kubiak and Armin Mustafa and Graeme Phillipson and Stephen Jolly and Simon Hadfield},
journal= {arXiv preprint arXiv:2404.12103},
year = {2024}
}
Comments
NTIRE workshop @ CVPR 2024. Code & models available at https://github.com/n-kubiak/S3R-Net